Cable Detection and Manipulation for {DLO}-in-Hole Assembly Tasks

This paper describes a cyber-physical system for the manipulation of Deformable Linear Objects (DLOs) addressing the DLO-in-hole insertion problem targeting an industrial sce-nario, the switchgear's components cabling task. In particular, the task considered is the insertion of DLOs in the switchgear components' holes. This task is very challenging since a precise knowledge of the DLO tip position and orientation is required for a successful operation. We tackled the DLO-in-hole problem from the computer vision perspective constraining our setup on employing just simple 2D images and by using the mobility of the robotic arm for achieving the full 3D knowledge of the DLOs. Then, the DLO tip is detected from two different image planes and the robot's trajectory corrected accordingly before insertion. To prove the effectiveness of the proposed solution, an example scenario is prepared and the method validated experimentally attempting the insertion of several DLOs in a sample switchgear component, obtaining an overall insertion success rate of 82.5 %.